Jannik Kossen
10 papers · 2020–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(7)
Learning Types · Machine Learning
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Natural Language Processing
(4)
Core AI
(3)
Resources & Methods
(3)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Optimization & Theory
(2)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
large language model
(4)
hallucination detection
(3)
acquisition strategy
(2)
in-context learning
(2)
active learning
(2)
model evaluation
(2)
few-shot learning
(1)
sample efficiency
(1)
representation learning
(1)
hyperparameter optimization
(1)
uncertainty quantification
(1)
video prediction
(1)
image retrieval
(1)
contrastive learning
(1)
uncertainty sampling
(1)
bayesian inference
(1)
nonparametric model
(1)
posterior predictive
(1)
semantic similarity
(1)
bayesian model
(1)
Papers
Rethinking Aleatoric and Epistemic Uncertainty
ICML 2025
Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation
EMNLP 2025
Estimating the Hallucination Rate of Generative AI
NeurIPS 2024
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
ICLR 2024
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
NeurIPS 2024
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
NeurIPS 2023
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
NeurIPS 2022
Active Testing: Sample-Efficient Model Evaluation
ICML 2021
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
NeurIPS 2021
Structured Object-Aware Physics Prediction for Video Modeling and Planning
ICLR 2020